© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100619
    Prev
    Next
    INDEX
    Explanations

    Japanese and full-width characters

    np_acts-logits-general · gemini-2.5-flash-lite

    Japanese and English text segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ן
    0.58
    тин
    0.57
     brutality
    0.55
     solvency
    0.55
    мма
    0.55
     gratefully
    0.54
    чей
    0.53
    рика
    0.53
     professora
    0.53
    тинен
    0.52
    POSITIVE LOGITS
    _
    0.79
    at
    0.72
    {
    0.68
    $
    0.64
    js
    0.60
    3
    0.60
    七
    0.60
    ing
    0.59
    _{
    0.59
    ET
    0.58
    Activations Density 0.000%

    No Known Activations